propose_amendment

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully carries the burden. It discloses key behavioral traits: supplies full replacement (not patch), SDK derives preimage and signs, and crucially, session state is not authoritative—amendments are ephemeral, lost on restart, and carry no external trust. This is exceptional transparency about side effects and trust implications, well beyond typical descriptions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tightly written sentences, each adding distinct information: purpose, replacement semantics, signing process, and ephemeral/trust limitation. The main purpose is front-loaded, and there is zero filler. Ideal conciseness with high information density.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema and no annotations, so the description must cover what an agent needs to invoke it. It tells the agent that a full CharterCore is required, that the SDK signs, and that the result is not persistent. It lacks an explicit statement about response format or that the charter_id must reference an existing charter, but these are not essential for a correct call. The description is nearly complete for a proposal tool in a complex domain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67% (4 of 6 parameters have descriptions). The description adds context about the SDK deriving the signing preimage and producing the proposer signature, which relates to the key parameters but does not explicitly explain proposer_private_key or proposer_public_key beyond their presence. It does clarify proposed_charter is a full replacement. With coverage above 50%, baseline is 3; the description provides marginal added value but does not fully compensate for undocumented key parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool proposes an amendment to a charter, specifies the resource (charter) and action (propose). It distinguishes from sibling tools like create_charter and sign_amendment by emphasizing it supplies a full replacement CharterCore, not a patch, and that the SDK produces the proposer signature. This uniquely identifies its role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage—proposing an amendment—but does not explicitly state when to use this tool over alternatives like sign_amendment or verify_amendment. It mentions the tool provides a full replacement, which hints at a choice, but lacks direct exclusions or cross-references to siblings. Context is clear but no explicit guidance on alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.